interactive-requirements-gathering

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Interactive Requirements Gathering

交互式需求收集

Structured framework for gathering requirements through interactive questionnaires. Based on the Conductor methodology's proven human-in-the-loop patterns.

这是一个通过交互式问卷收集需求的结构化框架，基于Conductor方法论中经过验证的“人在回路”模式。

When to Use

适用场景

Setting up new projects
Defining product requirements
Gathering feature specifications
Onboarding users to new workflows
Any task requiring structured user input

新项目启动
产品需求定义
功能规格收集
新工作流程用户入职
任何需要结构化用户输入的任务

Core Principles

核心原则

1. Question Classification

1. 问题分类

Before asking ANY question, classify its type:

Type	Purpose	Phrasing	Example
Additive	Brainstorming, multiple answers valid	"Select all that apply"	"Which features do you need?"
Exclusive	Single choice required	No multi-select phrase	"Which framework should we use?"

在提出任何问题之前，先对其类型进行分类：

类型	用途	表述方式	示例
Additive（可多选）	头脑风暴，允许多个答案	“请选择所有适用选项”	“你需要哪些功能？”
Exclusive（单选）	仅需一个答案	无多选提示语	“我们应该使用哪个框架？”

2. Question Structure

2. 问题结构

All questions MUST follow this structure:

[Question text]

A) [Option A - often recommended, marked with "(Recommended)"]
B) [Option B]
C) [Option C]
D) Type your own answer
E) Auto-generate and continue

所有问题必须遵循以下结构：

[问题文本]

A) [选项A - 通常为推荐选项，标注“(Recommended)”]
B) [选项B]
C) [选项C]
D) 输入自定义答案
E) 自动生成并继续

3. Sequential Questioning

3. 循序渐进式提问

CRITICAL: Ask ONE question at a time. Wait for response before next question.

CORRECT:
1. Ask Question 1
2. Wait for response
3. Confirm understanding
4. Ask Question 2

INCORRECT:
1. Ask Questions 1, 2, and 3 together

关键要求：一次只提一个问题。等待用户回复后再提出下一个问题。

正确做法：
1. 提出问题1
2. 等待回复
3. 确认理解
4. 提出问题2

错误做法：
1. 同时提出问题1、2、3

Questionnaire Workflow

问卷工作流程

Step 1: Introduction

步骤1：介绍

Announce the section you're working on:

"I'll now help you define [section name]. I'll ask a few questions to understand your needs."

告知用户当前正在处理的环节：

“我现在将帮你定义[环节名称]。我会提出几个问题来了解你的需求。”

Step 2: Sequential Questions

步骤2：循序渐进式提问

For each question:

Classify: Is this Additive or Exclusive?
Formulate: Create clear question with options
Present: Show options in A/B/C/D/E format
Wait: Do NOT proceed without response
Confirm: Summarize understanding before continuing

针对每个问题：

分类：确定是可多选（Additive）还是单选（Exclusive）类型？
设计：创建清晰的问题及选项
呈现：以A/B/C/D/E格式展示选项
等待：未收到回复前不要继续
确认：继续前先总结对用户需求的理解

Step 3: Handle Special Options

步骤3：处理特殊选项

Option D (Type your own):

Accept user's custom input
Confirm the custom response
Continue to next question

Option E (Auto-generate):

Stop asking questions for this section
Use best judgment based on previous answers
Generate content and present for review

选项D（输入自定义答案）：

接受用户的自定义输入
确认该自定义回复
继续下一个问题

选项E（自动生成）：

停止当前环节的提问
根据之前的回复做出最佳判断
生成内容并提交用户审核

Step 4: Generate Content

步骤4：生成内容

CRITICAL: Use ONLY the user's selected answers as source of truth.

CORRECT:
- User selected "OAuth 2.0" -> Generate OAuth implementation details

INCORRECT:
- Include Option A, B, C text that wasn't selected
- Include question text in generated content

关键要求：仅将用户选择的答案作为事实依据。

正确做法：
- 用户选择了“OAuth 2.0” -> 生成OAuth实现细节

错误做法：
- 包含未被选中的选项A、B、C的文本
- 在生成的内容中包含问题文本

Step 5: User Confirmation Loop

步骤5：用户确认循环

After generating content:

"I've drafted [document name]. Please review:"

[Content preview]

What would you like to do?
A) Approve - proceed to next step
B) Suggest Changes - tell me what to modify

Please respond with A or B.

Loop until approved or user provides alternative direction.

生成内容后：

“我已起草了[文档名称]，请审核：”

[内容预览]

你希望进行以下哪项操作？
A) 批准 - 进入下一步
B) 建议修改 - 告诉我需要调整的内容

请回复A或B。

循环此步骤直到用户批准或提供其他方向。

Question Patterns

问题模板

Product Vision Questions (Additive)

产品愿景问题（可多选）

What are the primary goals of this product? (Select all that apply)

A) Improve user productivity
B) Reduce operational costs
C) Enhance customer experience
D) Type your own answer
E) Auto-generate and continue

该产品的主要目标是什么？（请选择所有适用选项）

A) 提升用户生产力
B) 降低运营成本
C) 改善客户体验
D) 输入自定义答案
E) 自动生成并继续

Technology Selection Questions (Exclusive)

技术选型问题（单选）

Which database should we use?

A) PostgreSQL (Recommended) - Best for relational data with complex queries
B) MongoDB - Document store for flexible schemas
C) SQLite - Lightweight for small applications
D) Type your own answer
E) Auto-generate and continue

我们应该使用哪种数据库？

A) PostgreSQL (推荐) - 适用于需复杂查询的关系型数据
B) MongoDB - 用于灵活 schema 的文档型数据库
C) SQLite - 适用于小型应用的轻量级数据库
D) 输入自定义答案
E) 自动生成并继续

Feature Scoping Questions (Additive)

功能范围问题（可多选）

Which authentication methods should be supported? (Select all that apply)

A) Email/Password
B) OAuth (Google, GitHub)
C) Magic Links
D) Type your own answer
E) Auto-generate and continue

应支持哪些认证方式？（请选择所有适用选项）

A) 邮箱/密码
B) OAuth（Google、GitHub）
C) 魔法链接
D) 输入自定义答案
E) 自动生成并继续

Integration with AskUserQuestion Tool

与AskUserQuestion工具的集成

When using the AskUserQuestion tool, map to this framework:

javascript

AskUserQuestion({
  questions: [
    {
      header: 'Database',
      question: 'Which database should we use?',
      multiSelect: false, // Exclusive question
      options: [
        { label: 'PostgreSQL (Recommended)', description: 'Best for relational data' },
        { label: 'MongoDB', description: 'Document store for flexible schemas' },
        { label: 'SQLite', description: 'Lightweight for small apps' },
      ],
    },
  ],
});

使用AskUserQuestion工具时，需按照本框架进行映射：

javascript

AskUserQuestion({
  questions: [
    {
      header: 'Database',
      question: 'Which database should we use?',
      multiSelect: false, // 单选问题
      options: [
        { label: 'PostgreSQL (Recommended)', description: 'Best for relational data' },
        { label: 'MongoDB', description: 'Document store for flexible schemas' },
        { label: 'SQLite', description: 'Lightweight for small apps' },
      ],
    },
  ],
});

State Persistence

状态持久化

For multi-step questionnaires, save progress:

json

{
  "last_successful_step": "2.1_product_guide",
  "answers": {
    "product_type": "SaaS",
    "target_users": ["developers", "teams"]
  }
}

This enables resuming interrupted workflows.

对于多步骤问卷，需保存进度：